© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72755
    Prev
    Next
    INDEX
    Explanations

    u

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sample
    -0.54
    τό
    -0.49
     Soria
    -0.49
    Dies
    -0.49
    manta
    -0.49
     Sample
    -0.48
     diagnoses
    -0.48
     NSCoder
    -0.47
     Chwiliwch
    -0.47
    وائ
    -0.47
    POSITIVE LOGITS
    THROW
    0.49
    LEncoder
    0.47
    homonymie
    0.47
    ureusement
    0.46
    klju
    0.45
    createServer
    0.45
    consulté
    0.43
     GlobalKey
    0.43
     Locking
    0.43
     BorderRadius
    0.42
    Activations Density 0.001%

    No Known Activations